Presentation is loading. Please wait.

Presentation is loading. Please wait.

Understanding Faces 12/1/15 Some slides from Amin Sadeghi, Lana Lazebnik, Silvio Savarese, Fei-Fei Li Chuck Close, self portrait Lucas by Chuck Close Detection,

Similar presentations


Presentation on theme: "Understanding Faces 12/1/15 Some slides from Amin Sadeghi, Lana Lazebnik, Silvio Savarese, Fei-Fei Li Chuck Close, self portrait Lucas by Chuck Close Detection,"— Presentation transcript:

1 Understanding Faces 12/1/15 Some slides from Amin Sadeghi, Lana Lazebnik, Silvio Savarese, Fei-Fei Li Chuck Close, self portrait Lucas by Chuck Close Detection, Recognition, and Transformation of Faces

2 Exams back on Thursday

3 Face detection and recognition DetectionRecognition “Sally”

4 Applications of Face Recognition Digital photography

5 Applications of Face Recognition Digital photography Surveillance

6 Applications of Face Recognition Digital photography Surveillance Album organization

7 Consumer application: iPhoto 2009 http://www.apple.com/ilife/iphoto/

8 Consumer application: iPhoto 2009 Can be trained to recognize pets! http://www.maclife.com/article/news/iphotos_faces_recognizes_cats

9 Face detection Detection

10 What does a face look like?

11

12 What makes face detection hard? Expression

13 What makes face detection hard? Viewpoint

14 What makes face detection hard? Occlusion

15 What makes face detection hard? Distracting background

16 What makes face detection and recognition hard? Coincidental textures

17 Consumer application: iPhoto 2009 Things iPhoto thinks are faces

18 How to find faces anywhere in an image? Filter Image with a face?

19 19 Normalize mean and standard deviation Train a Filter SVM

20 Face detection: sliding windows … Filter/Template Multiple scales

21 What features? Exemplars (Sung Poggio 1994) Edge (Wavelet) Pyramids (Schneiderman Kanade 1998) Intensity Patterns (with NNs) (Rowley Baluja Kanade 1996) Haar Filters (Viola Jones 2000)

22 How to classify? Many ways – Neural networks – Adaboost – SVMs – Nearest neighbor

23 Face classifier Training Labels Training Images Classifier Training Training Image Features Testing Test Image Trained Classifier Face Prediction

24 Face recognition DetectionRecognition “Sally”

25 Face recognition Typical scenario: few examples per face, identify or verify test example What’s hard: changes in expression, lighting, age, occlusion, viewpoint Basic approaches (all nearest neighbor) 1.Project into a new subspace (or kernel space) (e.g., “Eigenfaces”=PCA) 2.Measure face features 3.Make 3d face model, compare shape+appearance (e.g., AAM)

26 Simple technique 1.Treat pixels as a vector 2.Recognize face by nearest neighbor

27 Most recent research focuses on “faces in the wild”, recognizing faces in normal photos – Classification: assign identity to face – Verification: say whether two people are the same Important steps 1.Detect 2.Align 3.Represent 4.Classify State-of-the-art Face Recognizers

28 Example of recent approach DeepFace: Closing the Gap to Human-Level Performance in Face Verification Taigman, Yang, Ranzato, & Wolf (Facebook, Tel Aviv), CVPR 2014 Following slides adapted from Daphne Tsatsoulis

29 Face Alignment 1. Detect a face and 6 fiducial markers using a support vector regressor (SVR) 2. Iteratively scale, rotate, and translate image until it aligns with a target face 3. Localize 67 fiducial points in the 2D aligned crop 4. Create a generic 3D shape model by taking the average of 3D scans from the USF Human-ID database and manually annotate the 67 anchor points 5.Fit an affine 3D-to-2D projection and use it to frontally warp the face

30 Train DNN classifier on aligned faces Architecture (deep neural network classifier) Two convolutional layers (with one pooling layer) 3 locally connected and 2 fully connected layers > 120 million parameters Train on dataset with 4400 individuals, ~1000 images each Train to identify face among set of possible people Face matching (verification) is done by comparing features at last layer for two faces

31 Results: Labeled Faces in the Wild Dataset Performs similarly to humans! (note: humans would do better with uncropped faces) Experiments show that alignment is crucial (0.97 vs 0.88) and that deep features help (0.97 vs. 0.91)

32 Transforming faces

33 Figure-centric averages Need to Align Position Scale Orientation Antonio Torralba & Aude Oliva (2002) Averages: Hundreds of images containing a person are averaged to reveal regularities in the intensity patterns across all the images.

34 How do we average faces? http://www2.imm.dtu.dk/~aam/datasets/datasets.html

35 morphing Morphing image #1image #2 warp

36 Cross-Dissolve vs. Morphing Average of Appearance Vectors Images from James Hays Average of Shape Vectors http://www.faceresearch.org/ demos/vector

37 Aligning Faces Need to Align Position Scale Orientation Key-points The more key-points, the finer alignment Images from Alyosha Efros

38 Appearance Vectors vs. Shape Vectors 200*150 pixels (RGB) Vector of 200*150*3 Dimensions Appearance Vector 43 coordinates (x,y) Shape Vector Vector of 43*2 Dimensions

39 Average of two Faces 1.Input face keypoints 2.Pairwise average keypoint coordinates 3.Triangulate the faces 4.Warp: transform every face triangle 5.Average the pixels

40 Average of multiple faces 1. Warp to mean shape 2. Average pixels http://graphics.cs.cmu.edu/courses/15-463/2004_fall/www/handins/brh/final/ http://www.faceresearch.org/demos/average

41 Average Men of the world

42 Average Women of the world

43 Subpopulation means Other Examples: – Average Kids – Happy Males – Etc. – http://www.faceresearch.org http://www.faceresearch.org Average male Average female Average kid Average happy male

44 How to represent variations? Training images x 1,…,x N

45 PCA General dimensionality reduction technique Finds major directions of variation Preserves most of variance with a much more compact representation – Lower storage requirements (eigenvectors + a few numbers per face) – Faster matching/retrieval

46 Principal Component Analysis Given a point set, in an M -dim space, PCA finds a basis such that – The most variation is in the first basis vector – The second most, in the second vector that is orthogonal to the first vector – The third… x1x1 x0x0 x1x1 x0x0 1 st principal component 2 nd principal component 1 st principal component 2 nd principal component

47 PCA in MATLAB x=rand(3,10);%10 3D examples mu=mean(x,2); x_norm = x-repmat(mu,[1 n]); x_covariance = x_norm*x_norm'; [U, E] = eig(x_covariance) U = 0.74 0.07 -0.66 0.65 0.10 0.74 -0.12 0.99 -0.02 E = 0.27 0 0 0 0.63 0 0 0 0.94

48 Principal Component Analysis Choosing subspace dimension r : look at decay of the eigenvalues as a function of r Larger r means lower expected error in the subspace data approximation rM1 eigenvalues First r < M basis vectors provide an approximate basis that minimizes the mean-squared-error (MSE) of reconstructing the original points

49 Eigenfaces example (PCA of face images) Top eigenvectors: u 1,…u k Mean: μ

50 Visualization of eigenfaces (appearance variation) Principal component (eigenvector) u k μ + 3σ k u k μ – 3σ k u k

51 Face Space How to find a set of directions to cover all space? We call these directions Basis If number of basis faces is large enough to span the face subspace: Any new face can be represented as a linear combination of basis vectors.

52 Limitations of Global appearance method: not robust to misalignment, background variation

53 Can represent face in appearance or shape space 200*150 pixels (RGB) Appearance Vector 43 coordinates (x,y) Shape Vector

54 First 3 Shape Bases with PCA Mean appearance http://graphics.cs.cmu.edu/courses/15-463/2004_fall/www/handins/brh/final/

55 Manipulating faces How can we make a face look more female/male, young/old, happy/sad, etc.? http://www.faceresearch.org/demos/transform Current face Prototype 2 Prototype 1

56 Manipulating faces We can imagine various meaningful directions. Current face Masculine Feminine Happy Sad

57 Psychological Attributes

58 Human Perception

59

60

61

62

63

64 Which face is more attractive? original beautified http://leyvand.com/beautification2008/

65 System Overview http://leyvand.com/beautification2008/

66 Things to remember Face Detection: train face vs. non-face model and scan over multi-scale image Face Recognition: detect, align, compute features, and compute similarity Represent faces with an appearance vector and a shape vector Use PCA for compression or to model main directions of variance Can transform faces by moving shape vector in a given direction and warping


Download ppt "Understanding Faces 12/1/15 Some slides from Amin Sadeghi, Lana Lazebnik, Silvio Savarese, Fei-Fei Li Chuck Close, self portrait Lucas by Chuck Close Detection,"

Similar presentations


Ads by Google